© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8802
    Prev
    Next
    INDEX
    Explanations

    second person pronouns and associated auxiliary verbs, often in the context of helpfulness or ensuring resources or support.

    oai_token-act-pair · gemini-2.0-flash

    instructions and advice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    цуз
    -0.59
     itſelf
    -0.58
     Middles
    -0.58
    ThemeOverlay
    -0.57
     vrai
    -0.55
    ("/:
    -0.55
     Estar
    -0.54
    #+#
    -0.54
     pedest
    -0.54
    WithMany
    -0.53
    POSITIVE LOGITS
    tagHelperRunner
    0.61
    AccessorTable
    0.52
     to
    0.52
    utilisons
    0.51
     don
    0.50
    apnews
    0.50
    imetsu
    0.48
     won
    0.47
    hui
    0.47
    WebVitals
    0.46
    Activations Density 4.167%

    No Known Activations